can1357 5617184356 chore(react-edit-benchmark/runs): added GPT-5.3 Codex benchmark runs with three edit variants ...

- Added three new benchmark run reports for GPT-5.3 Codex model with different edit variants (hashline, patch, replace).
- Recorded performance metrics across 60 tasks per variant with success rates ranging from 80-83.3%.

2026-02-12 20:29:22 +01:00

..

claude-haiku-4-5_hashline_2026-02-11T06-43-50.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

claude-haiku-4-5_patch_2026-01-19T12-20-37.md

feat: enhanced patch applicator with fallback variants and fuzzy matching

2026-01-19 16:16:55 +01:00

claude-haiku-4-5_patch_2026-01-19T12-23-33.md

feat: enhanced patch applicator with fallback variants and fuzzy matching

2026-01-19 16:16:55 +01:00

claude-haiku-4-5_patch_2026-01-19T12-39-17.md

feat: enhanced patch applicator with fallback variants and fuzzy matching

2026-01-19 16:16:55 +01:00

claude-haiku-4-5_patch_2026-01-19T13-18-16.md

feat: enhanced patch applicator with fallback variants and fuzzy matching

2026-01-19 16:16:55 +01:00

claude-haiku-4-5_patch_2026-01-19T13-33-14.md

feat: enhanced patch applicator with fallback variants and fuzzy matching

2026-01-19 16:16:55 +01:00

claude-haiku-4-5_patch_2026-01-19T13-50-38.md

feat: enhanced patch applicator with fallback variants and fuzzy matching

2026-01-19 16:16:55 +01:00

claude-haiku-4-5_patch_2026-02-10T15-13-20.md

feat(coding-agent/patch): enhanced hashline edits to strip prefixes and preserve whitespace-only changes

2026-02-10 17:17:26 +01:00

claude-haiku-4-5_patch_2026-02-11T06-05-06.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

claude-haiku-4-5_replace_2026-02-11T06-04-50.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

claude-sonnet-4_5_hashline_2026-02-11T05-45-11.md

feat(coding-agent): enhanced hashline edit tool with whitespace normalization, error recovery, and diagnostic improvements

2026-02-11 08:12:08 +01:00

claude-sonnet-4_5_patch_2026-02-11T05-45-04.md

feat(coding-agent): enhanced hashline edit tool with whitespace normalization, error recovery, and diagnostic improvements

2026-02-11 08:12:08 +01:00

claude-sonnet-4_5_patch_2026-02-11T06-06-43.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

claude-sonnet-4_5_replace_2026-02-11T05-45-21.md

feat(coding-agent): enhanced hashline edit tool with whitespace normalization, error recovery, and diagnostic improvements

2026-02-11 08:12:08 +01:00

claude-sonnet-4_5_replace_2026-02-11T06-06-53.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

claude-sonnet-4-5_patch_2026-02-10T15-03-14.md

feat(coding-agent/patch): enhanced hashline edits to strip prefixes and preserve whitespace-only changes

2026-02-10 17:17:26 +01:00

deepseek-v3_2_hashline_2026-02-11T09-41-20.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

deepseek-v3_2_patch_2026-02-11T09-41-36.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

deepseek-v3_2_replace_2026-02-11T09-40-34.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

devstral-medium_hashline_2026-02-11T09-35-48.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

devstral-medium_patch_2026-02-11T09-38-39.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

devstral-medium_replace_2026-02-11T09-35-12.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

gemini-2_5-flash-lite_hashline_2026-02-10T16-40-51.md

feat(hashline): refactored HashlineEdit API with unified range syntax and added benchmark reports

2026-02-10 17:48:23 +01:00

gemini-2_5-flash-lite_patch_2026-02-10T15-39-13.md

feat(coding-agent/patch): enhanced hashline edits to strip prefixes and preserve whitespace-only changes

2026-02-10 17:17:26 +01:00

gemini-2_5-flash-lite_patch_2026-02-11T04-59-39.md

feat(coding-agent): enhanced hashline edit tool with whitespace normalization, error recovery, and diagnostic improvements

2026-02-11 08:12:08 +01:00

gemini-2_5-flash-lite_replace_2026-02-11T04-59-14.md

feat(coding-agent): enhanced hashline edit tool with whitespace normalization, error recovery, and diagnostic improvements

2026-02-11 08:12:08 +01:00

gemini-3-flash_hashline_2026-02-11T08-44-04.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

gemini-3-flash_patch_2026-02-11T06-05-11.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

gemini-3-flash_replace_2026-02-11T06-06-08.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

glm-4_5-air_hashline_2026-02-11T04-59-01.md

feat(coding-agent): enhanced hashline edit tool with whitespace normalization, error recovery, and diagnostic improvements

2026-02-11 08:12:08 +01:00

glm-4_5-air_patch_2026-02-10T17-35-53.md

fix(coding-agent/patch): fixed line hash computation to normalize whitespace and remove index dependency

2026-02-10 18:41:41 +01:00

glm-4_5-air_patch_2026-02-11T04-50-49.md

feat(coding-agent): enhanced hashline edit tool with whitespace normalization, error recovery, and diagnostic improvements

2026-02-11 08:12:08 +01:00

glm-4_5-air_patch_2026-02-11T06-10-55.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

glm-4_5-air_replace_2026-02-11T04-50-01.md

feat(coding-agent): enhanced hashline edit tool with whitespace normalization, error recovery, and diagnostic improvements

2026-02-11 08:12:08 +01:00

glm-4_5-air_replace_2026-02-11T06-10-21.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

glm-4_7_patch_2026-02-10T17-39-32.md

fix(coding-agent/patch): fixed line hash computation to normalize whitespace and remove index dependency

2026-02-10 18:41:41 +01:00

gpt-5_1-codex-mini_hashline_2026-02-11T09-29-46.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

gpt-5_1-codex-mini_patch_2026-01-19T13-42-23.md

feat: enhanced patch applicator with fallback variants and fuzzy matching

2026-01-19 16:16:55 +01:00

gpt-5_1-codex-mini_patch_2026-01-19T13-54-55.md

feat: enhanced patch applicator with fallback variants and fuzzy matching

2026-01-19 16:16:55 +01:00

gpt-5_1-codex-mini_patch_2026-01-19T14-49-47.md

style: reformatted TypeScript code formatting and added benchmark reports

2026-01-19 16:22:47 +01:00

gpt-5_1-codex-mini_patch_2026-01-19T15-05-03.md

style: reformatted TypeScript code formatting and added benchmark reports

2026-01-19 16:22:47 +01:00

gpt-5_1-codex-mini_patch_2026-02-10T16-05-12.md

feat(coding-agent/patch): enhanced hashline edits to strip prefixes and preserve whitespace-only changes

2026-02-10 17:17:26 +01:00

gpt-5_1-codex-mini_replace_2026-02-11T09-26-14.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

gpt-5_2-codex_hashline_2026-02-11T07-25-36.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

gpt-5_2-codex_patch_2026-02-11T07-19-41.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

gpt-5_2-codex_replace_2026-02-11T06-56-09.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

gpt-5_3-codex_hashline_2026-02-12T18-12-01.md

chore(react-edit-benchmark/runs): added GPT-5.3 Codex benchmark runs with three edit variants

2026-02-12 20:29:22 +01:00

gpt-5_3-codex_patch_2026-02-12T18-12-40.md

chore(react-edit-benchmark/runs): added GPT-5.3 Codex benchmark runs with three edit variants

2026-02-12 20:29:22 +01:00

gpt-5_3-codex_replace_2026-02-12T18-15-09.md

chore(react-edit-benchmark/runs): added GPT-5.3 Codex benchmark runs with three edit variants

2026-02-12 20:29:22 +01:00

grok-4-1-fast_hashline_2026-02-11T08-49-14.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

grok-4-1-fast_patch_2026-02-11T08-24-44.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

grok-4-1-fast_replace_2026-02-11T09-13-21.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

grok-4-fast-non-reasoning_hashline_2026-02-11T08-39-28.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

grok-4-fast-non-reasoning_patch_2026-02-10T15-29-33.md

feat(coding-agent/patch): enhanced hashline edits to strip prefixes and preserve whitespace-only changes

2026-02-10 17:17:26 +01:00

grok-4-fast-non-reasoning_patch_2026-02-11T06-04-36.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

grok-4-fast-non-reasoning_replace_2026-02-11T06-04-06.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

grok-code-fast-1_hashline_2026-02-11T08-27-24.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

grok-code-fast-1_patch_2026-02-11T08-35-38.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

grok-code-fast-1_replace_2026-02-11T09-24-06.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

kimi-k2_5_hashline_2026-02-11T08-58-08.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

kimi-k2_5_patch_2026-02-11T07-14-30.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

kimi-k2_5_replace_2026-02-11T07-39-12.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

minimax-m2_1_hashline_2026-02-11T09-33-40.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

minimax-m2_1_patch_2026-02-11T09-37-00.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

minimax-m2_1_replace_2026-02-11T09-34-23.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

qwen-turbo_hashline_2026-02-11T06-50-08.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

qwen-turbo_patch_2026-02-11T06-10-23.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

qwen-turbo_replace_2026-02-11T06-09-29.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

zai-glm-4_7_hashline_2026-02-11T08-25-55.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

zai-glm-4_7_patch_2026-02-11T08-32-00.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00

zai-glm-4_7_replace_2026-02-11T09-18-06.md

chore(react-edit-benchmark/runs): updated benchmark reports for 15 models with new test results and variants

2026-02-11 10:51:28 +01:00